| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9345794392523364, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018691588785046728, | |
| "eval_loss": 10.380106925964355, | |
| "eval_runtime": 0.1712, | |
| "eval_samples_per_second": 525.719, | |
| "eval_steps_per_second": 70.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 0.042673755437135696, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "eval_loss": 10.379865646362305, | |
| "eval_runtime": 0.1712, | |
| "eval_samples_per_second": 525.844, | |
| "eval_steps_per_second": 70.112, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 0.03669259324669838, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3784, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 0.04349780082702637, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "eval_loss": 10.379013061523438, | |
| "eval_runtime": 0.1698, | |
| "eval_samples_per_second": 529.918, | |
| "eval_steps_per_second": 70.656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 0.042363181710243225, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.379, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 0.04922573268413544, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2803738317757009, | |
| "eval_loss": 10.377721786499023, | |
| "eval_runtime": 0.1729, | |
| "eval_samples_per_second": 520.526, | |
| "eval_steps_per_second": 69.404, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 0.04994016885757446, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3767, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "eval_loss": 10.37624454498291, | |
| "eval_runtime": 0.1945, | |
| "eval_samples_per_second": 462.625, | |
| "eval_steps_per_second": 61.683, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3925233644859813, | |
| "grad_norm": 0.06224982813000679, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 10.3755, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 0.07088863849639893, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 10.3739, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4672897196261682, | |
| "eval_loss": 10.374489784240723, | |
| "eval_runtime": 0.1721, | |
| "eval_samples_per_second": 522.823, | |
| "eval_steps_per_second": 69.71, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5046728971962616, | |
| "grad_norm": 0.08333060145378113, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 10.3734, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "grad_norm": 0.08638530224561691, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3719, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5607476635514018, | |
| "eval_loss": 10.372705459594727, | |
| "eval_runtime": 0.1771, | |
| "eval_samples_per_second": 508.112, | |
| "eval_steps_per_second": 67.748, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.616822429906542, | |
| "grad_norm": 0.09677360951900482, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 10.3714, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6542056074766355, | |
| "eval_loss": 10.371152877807617, | |
| "eval_runtime": 0.1738, | |
| "eval_samples_per_second": 517.918, | |
| "eval_steps_per_second": 69.056, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6728971962616822, | |
| "grad_norm": 0.10105115175247192, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 10.3709, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7289719626168224, | |
| "grad_norm": 0.12131473422050476, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 10.3694, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7476635514018691, | |
| "eval_loss": 10.370113372802734, | |
| "eval_runtime": 0.1729, | |
| "eval_samples_per_second": 520.643, | |
| "eval_steps_per_second": 69.419, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7850467289719626, | |
| "grad_norm": 0.12438107281923294, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.3694, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8411214953271028, | |
| "grad_norm": 0.1044248566031456, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3692, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8411214953271028, | |
| "eval_loss": 10.36966609954834, | |
| "eval_runtime": 0.1736, | |
| "eval_samples_per_second": 518.406, | |
| "eval_steps_per_second": 69.121, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.897196261682243, | |
| "grad_norm": 0.11366444826126099, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 10.3696, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.9345794392523364, | |
| "eval_loss": 10.369586944580078, | |
| "eval_runtime": 0.1789, | |
| "eval_samples_per_second": 503.117, | |
| "eval_steps_per_second": 67.082, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5577533030400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |